NeumTry / NeumAI
Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.
☆853Updated last year
Alternatives and similar repositories for NeumAI:
Users that are interested in NeumAI are comparing it to the libraries listed below
- LLMFlows - Simple, Explicit and Transparent LLM Apps☆689Updated last month
- A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for vario…☆1,010Updated last month
- Agents Capable of Self-Editing Their Prompts / Python Code☆760Updated last year
- Data-Driven Evaluation for LLM-Powered Applications☆484Updated 2 months ago
- Text analytics for LLM apps. Cluster messages to detect use cases, outliers, power users. Detect intents and run evals with LLM (OpenAI, …☆426Updated last week
- Prompt engineering for developers☆679Updated last year
- An LLM-powered advanced RAG pipeline built from scratch☆831Updated last year
- A tiny nearest-neighbor embedding database built with SQLite and Pytorch. (In development!)☆769Updated last year
- A reactive runtime for building durable AI agents☆1,310Updated 2 months ago
- Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python…☆1,348Updated 2 months ago
- Complex LLM Workflows from Simple JSON.☆294Updated last year
- Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastr…☆1,550Updated this week
- Action library for AI Agent☆212Updated this week
- Edge full-stack LLM platform. Written in Rust☆378Updated 10 months ago
- AgentSearch is a framework for powering search agents and enabling customizable local search.☆481Updated 11 months ago
- Get 100% uptime, reliability from OpenAI. Handle Rate Limit, Timeout, API, Keys Errors☆650Updated last year
- Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework☆338Updated 4 months ago
- 🧠 Motorhead is a memory and information retrieval server for LLMs.☆868Updated 4 months ago
- Enforce structured output from LLMs 100% of the time☆249Updated 8 months ago
- Vision utilities for web interaction agents 👀☆1,631Updated 4 months ago
- This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.☆1,203Updated this week
- ☆742Updated 11 months ago
- Classify and extract structured data with LLMs☆426Updated last year
- LLM fine-tuning and eval☆344Updated last year
- A realtime serving engine for Data-Intensive Generative AI Applications☆984Updated this week
- A lightweight task engine for building stateful AI agents that prioritizes simplicity and flexibility.☆914Updated this week
- Build agents which are controlled by LLMs☆973Updated 2 months ago
- Finetune llama2-70b and codellama on MacBook Air without quantization☆448Updated last year
- VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of y…☆691Updated 10 months ago
- LLM(😽)☆1,661Updated last month